INDEX
    Explanations

    terms and references related to a specific film or artistic project

    New Auto-Interp
    Negative Logits
    opers
    -0.16
    addon
    -0.16
    PTS
    -0.15
    .sap
    -0.14
    oine
    -0.14
    pers
    -0.14
    neighbors
    -0.14
    ationship
    -0.14
    fre
    -0.13
    mill
    -0.13
    POSITIVE LOGITS
    edin
    0.21
    allas
    0.19
    awa
    0.18
    tol
    0.16
    pron
    0.16
    erk
    0.15
    usted
    0.15
    uder
    0.15
    om
    0.14
    erdem
    0.14
    Act Density 0.073%

    No Known Activations